More than a decade ago few companies intentionally penetrated and successfully drilled the large salt sections in the Gulf of Mexico (GoM). Problems common to drilling in salt led to excessive nonproductive time (NPT): hole instability, stuck pipe, tools lost in hole, among others. Although techniques are now available that enable successful drilling of many of these large salt structures, there still are some formations with characteristics that make drilling challenging. This paper focuses on one such ultradeep subsalt prospect and the strategies used to overcome the key issues of nonhomogeneous salt formations, shock and vibration, and salt inclusions. Application of new and emerging technologies and techniques for drilling in similar environments focused on drilling parameter optimization, bottomhole assembly (BHA) tendencies, and stuck-pipe analysis. This paper presents comparisons of the results expected prior to optimization measures and the actual results.

Downhole vibration remains a major challenge for drillers. Today, there is technology to look at the problem from a unique perspective. A novel look at the problem focuses on evaluation of machine learning algorithms to predict downhole vibrations. Prediction is the first step in a longer road map. The goal would be to find an optimal combination of revolutions per minute (RPM) and weight-on-bit (WOB) to remedy drilling vibration in real-time, hence closing the loop. Drilling mechanics data for thousands of wells, acquired over more than ten years was analyzed. Some preparation of the drilling mechanics data was required. Data cleaning was first performed. This included corrections for time-dependent nature of the data. Data imputing for missing values and handling of outliers and anomalies was also performed in this stage. This was followed by feature engineering which included adding variables based on company-wide drilling domain expertise. Variables to capture data patterns and variables for better capturing the time-series dependencies were also created in this stage. This paper will discuss methodologies and general rules that were tested for preparing unstructured drilling data. A few of the machine learning algorithms used as building blocks of our full solution are gradient boosting and random forest. Deep learning models were also tested and the value of these are compared. The results were compiled to decide the best algorithm which could further be used to fine-tune optimum performance. The time series aspect of the data is captured in a moving window. As the window increases, the performance of each algorithm also varied. Also, evaluation of the benefits and drawbacks of each algorithm for the drilling predictions is detailed. Ways to improve the accuracy of prediction for downhole vibrations is also suggested with reference to the results showing the logic behind all recommendations. There will be a summary of the details of each finding and a short discussion on the way forward for the industry.

Since the early 1920s, sensors have been used on drilling rigs to enable making operations decisions. Drilling operators have always relied on human intervention whenever the data were questionable. Automation, remote operations, smart systems and digital technology are all words which describe the recent directional change for well construction. These changes can have a huge impact on the efficiency, safety and cost of operations. The drilling industry needs real time validation of data. With the volume of data being generated on today's rigs, this requires measures beyond human capacity. There are many gaps which need to be addressed if the industry is to make this standard in the future. For example, to make automation to work, the data fed into the smart systems for decision making must be cleaned, corrected and calibrated. This paper presents how machine learning techniques from other industries can be modified and applied to the data from drilling rig sensors. There are numerous strategies employed in medical, space and government agencies where validating data has been important to success. Of these strategies, a few were selected for drilling operation applications. An auto-encoder was used to study low dimensional data representations in an unsupervised manner. This algorithm was then adjusted to allow for partial reconstruction and handling processed drilling data. Reconstruction errors were used as a metric to identify potential errors and highlight them for the domain experts. Additionally, to identify errors, artificial potential errors were injected into the system and then the system was tested to understand if the errors could be identified by our methods. The results show that we can correctly identify anomalies such as missing data, outliers and sensor drift, using reconstruction errors. The model presented in this paper is based on drilling data from thousands of wells and tested on additional data as well as simulated data.

A significant contribution that some oilfield services companies provide for drilling operators today is directional well planning. A major task in the process is to identify and analyze the risk of wellbore collisions. If there is a risk of collision beyond acceptable limits, risk management must be applied. The first part of this process is to collect data. The second step is to analyze the potential risk. The risk not only involves a financial aspect but also HSE (Health Safety and Environmental), so it is imperative that we make the right decision using the most effective tools. Failure to take the right precautions may result in potentially catastrophic human and environmental implications. Generally this is already a complicated task. It gets particularly complicated when this is done at high latitudes and in certain wellbore orientations. Much of the industry today still believes that wellbores are represented accurately by surveys. While in the majority of cases this is somewhat true, the uncertainty and probabilistic nature of the measurement is often overlooked or misunderstood. Few people in the industry today actually understand how this translates to anti-collision also known as collision avoidance. Even fewer understand how much effect your latitude can have on this type of calculation. This paper will address these complications. After a short overview on wellbore placement, the paper will first discuss some theory on what makes high latitude wellbore placement challenging and when is it a relevant consideration. How it relates to collision avoidance will be explained. The current gaps in the industry today will be revealed and options to close those gaps are discussed. Upcoming technologies for reducing risk are reviewed. The second part of the paper will focus on risk management; namely mitigation and prevention. Case studies will be reviewed. Common misconceptions will be eliminated. The paper will attempt to set a foundation of understanding of the fundamental important considerations for anyone involved in collision avoidance in high latitude locations such as the Arctic.

In 1919 the world record for the deepest well was broken by the Hope natural gas company with a total depth (TD) of 7,579 ft. Although it took over 3 years to reach TD, only 325 days were spent actually drilling. Today in deepwater operations, the water depth alone can exceed this record, and operators have drilled past 30,000 ft in just 4 or 5 months. Technology and procedures have evolved extensively as operations that appeared impossible a decade ago are now considered routine. Today, operators are being pushed more than before, not just to explore deeper prospects, but also to get there efficiently. The future of the industry depends on it. Now there are new questions the industry is asking about deep water: What is different about drilling deep in deepwater operations? What does it actually take to drill the deepest wells in the world today? Currently, there are only a handful of personnel with the knowledge and experience to execute these wells. This paper will discuss the challenges of planning and drilling directional wells in excess of 30,000 ft true vertical depth (TVD) and will also look at lessons from some of the major deepwater Gulf of Mexico (GoM) operations that have successfully drilled wells beyond this mark and are continuing to push the envelope further. These wells have held, at one time or another, records for deepest wells drilled in many categories in recent years. IntroductionMany of the deepest wells in the world have been drilled in the GoM, and many have been in deep water. Fig. 1 illustrates the trends in total TVD of the wells for the GoM. Fig. 2 illustrates the trend in increasing water depths with time for wells in the GoM. The direction that the industry is heading in is deeper: deeper water and deeper wells. The technology exists to take us there. However, there are critical factors to consider when planning these wells.